Springer, 2016. — 284 p.Image processing and pattern recognition emerge as important components of decision support systems for industrial, medical, military applications, among others. Several methods have been presented in the literature to solve image processing and pattern recognition tasks. They require some method-specific parameters to be optimally tuned in order to achieve the best performance. Such requirement has naturally steered both methods toward being converted into optimization problems. Optimization has a fundamental importance in solving many problems in image processing and pattern recognition. Such a fact is evident from a quick look at special issues, congresses, and specialized journals that focus on such areas, where a significant number of manuscripts report on the use of optimization techniques. Classical optimization methods often face great difficulties while dealing with images or systems containing noise and distortions. Under such conditions, the use of evolutionary computation approaches has been recently extended to address challenging real-world image processing and pattern recognition problems. Image processing and pattern recognition are both dynamic and fast moving fields of research. Each new approach that is developed by engineers, mathematicians, and computer scientists is quickly identified, understood, and assimilated in order to be applied to image processing and pattern recognition problems. In this book, we strive to bring some state-of-the-art techniques by using recent results in evolutionary computation after its application to challenging and significant problems in image processing and pattern recognition. Evolutionary computation methods are vast and have many variants. There exist a rich amount of literature on the subject, including textbooks, tutorials, and journal papers that cover in detail practically every aspect of the field. The great amount of information available makes it difficult for no specialist to explore the literature and to find the right optimization technique for a specific image or pattern recognition application. Therefore, any attempt to present the whole area of evolutionary computation in detail would be a daunting task, probably doomed to failure. This task would be even more difficult if the goal is to understand the applications of evolutionary methods in the context of image processing and pattern recognition. For this reason, the best practice is to consider only a representative set of evolutionary approaches, just as it has been done in this book. The aim of this book was to provide an overview of the different aspects of evolutionary methods in order to enable the reader in reaching a global understanding of the field and in conducting studies on specific evolutionary techniques that are related to applications in image processing and pattern recognition that for some reason attract his interest. Our goal is to bridge the gap between recent evolutionary optimization techniques and novel image processing methods that profit on the convenient properties of evolutionary methods. To do this, at each chapter, we endeavor to explain basic ideas of the proposed applications in ways that can be understood by readers who may not possess the necessary backgrounds on either of the fields. Therefore, image processing and pattern recognition practitioners who are not evolutionary computation researchers will appreciate that the techniques discussed are beyond simple theoretical tools since they have been adapted to solve significant problems that commonly arise on such areas. On the other hand, members of the evolutionary computation community can learn the way in which image processing and pattern recognition problems can be translated into an optimization task.Introduction. Image Segmentation Based on Differential Evolution Optimization. Motion Estimation Based on Artificial Bee Colony (ABC). Ellipse Detection on Images Inspired by the Collective Animal Behavior. Template Matching by Using the States of Matter Algorithm. Estimation of Multiple View Relations Considering Evolutionary Approaches. Circle Detection on Images Based on an Evolutionary Algorithm that Reduces the Number of Function Evaluations. Otsu and Kapur Segmentation Based on Harmony Search Optimization. Leukocyte Detection by Using Electromagnetism-like Optimization. Automatic Segmentation by Using an Algorithm Based on the Behavior of Locust Swarms. A: RANSAC Algorithm. B: List of Benchmark Functions.
Чтобы скачать этот файл зарегистрируйтесь и/или войдите на сайт используя форму сверху.